feat: new Vectara RAG Component (#2733)
* First implementation of LangWatch tracer * Remove dependency from backend base internal and add langwatch docs * Bump langwatch to v0.1.4 * Fix missing log parameter on method * Move docs to the right folder * chore: update lock * Add Vectara RAG component and docs * [autofix.ci] apply automated fixes * refactor: update VectaraRAG component to the new component standard * fix: update VectaraRagComponent filter parameter Update the filter parameter in the VectaraRagComponent class to use the correct variable name 'self.filter' instead of 'filter'. This ensures that the correct filter value is passed to the VectaraQueryConfig object. * fix: add condition to set_cache_coro in Graph class Add a condition to the `set_cache_coro` function call in the `Graph` class. The condition checks if the `cache` variable is true and the `flow_id` is not empty before calling the function. This ensures that the cache is set only when both conditions are met, improving the efficiency of the code. --------- Co-authored-by: Rogério Chaves <rogeriochaves@users.noreply.github.com> Co-authored-by: Gabriel Luiz Freitas Almeida <gabriel@langflow.org> Co-authored-by: autofix-ci[bot] <114827586+autofix-ci[bot]@users.noreply.github.com>
This commit is contained in:
David Oplatka
GitHub
parent
8fffe73050
commit
469625c0a3
7 changed files with 222 additions and 17 deletions
127
src/backend/base/langflow/components/vectorstores/vectara_rag.py
Normal file
127
src/backend/base/langflow/components/vectorstores/vectara_rag.py
Normal file
|
|
@ -0,0 +1,127 @@
|
|||
from langflow.custom import Component
|
||||
from langflow.field_typing.range_spec import RangeSpec
|
||||
from langflow.io import DropdownInput, FloatInput, IntInput, MessageTextInput, Output
|
||||
from langflow.schema.message import Message
|
||||
|
||||
|
||||
class VectaraRagComponent(Component):
|
||||
display_name = "Vectara RAG"
|
||||
description = "Vectara's full end to end RAG"
|
||||
documentation = "https://docs.vectara.com/docs"
|
||||
icon = "Vectara"
|
||||
name = "VectaraRAG"
|
||||
SUMMARIZER_PROMPTS = [
|
||||
"vectara-summary-ext-24-05-sml",
|
||||
"vectara-summary-ext-24-05-med-omni",
|
||||
"vectara-summary-ext-24-05-large",
|
||||
"vectara-summary-ext-24-05-med",
|
||||
"vectara-summary-ext-v1.3.0",
|
||||
]
|
||||
|
||||
RERANKER_TYPES = ["mmr", "rerank_multilingual_v1", "none"]
|
||||
|
||||
field_order = ["vectara_customer_id", "vectara_corpus_id", "vectara_api_key", "search_query", "reranker"]
|
||||
# return {
|
||||
# "vectara_customer_id": {"display_name": "Vectara Customer ID", "field_type": "str", "required": True},
|
||||
# "vectara_corpus_id": {"display_name": "Vectara Corpus ID", "field_type": "str", "required": True},
|
||||
# "vectara_api_key": {"display_name": "Vectara API Key", "field_type": "str", "required": True},
|
||||
# "search_query": {"display_name": "Search Query", "field_type": "str", "info": "The query to receive an answer on.", "required": True},
|
||||
# "lexical_interpolation": {"display_name": "Hybrid Search Factor", "field_type": "float", "value": 0.005, "info": "How much to weigh lexical scores compared to the embedding score. 0 means lexical search is not used at all, and 1 means only lexical search is used.", "advanced": True},
|
||||
# "filter": {"display_name": "Metadata Filters", "field_type": "str", "value": '', "info": "The filter string to narrow the search to according to metadata attributes.", "advanced": True},
|
||||
# "reranker": {"display_name": "Reranker Type", "options": RERANKER_TYPES, "value": RERANKER_TYPES[0], "info": "How to rerank the retrieved search results."},
|
||||
# "reranker_k": {"display_name": "Number of Results to Rerank", "field_type": "int", "value": 50, "advanced": True},
|
||||
# "diversity_bias": {"display_name": "Diversity Bias", "field_type": "float", "value": 0.2, "info": "Ranges from 0 to 1, with higher values indicating greater diversity (only applies to MMR reranker).", "advanced": True},
|
||||
# "max_results": {"display_name": "Max Results to Summarize", "field_type": "int", "value": 7, "info": "The maximum number of search results to be available to the prompt.", "advanced": True},
|
||||
# "response_lang": {"display_name": "Response Language", "field_type": "str", "value": "eng", "info": "Use the ISO 639-1 or 639-3 language code or auto to automatically detect the language.", "advanced": True},
|
||||
# "prompt": {"display_name": "Prompt Name", "options": SUMMARIZER_PROMPTS, "value": SUMMARIZER_PROMPTS[0], "info": "Only vectara-summary-ext-24-05-sml is for Growth customers; all other prompts are for Scale customers only.", "advanced": True}
|
||||
# }
|
||||
|
||||
inputs = [
|
||||
MessageTextInput(name="search_query", display_name="Search Query", info="The query to receive an answer on."),
|
||||
FloatInput(
|
||||
name="lexical_interpolation",
|
||||
display_name="Hybrid Search Factor",
|
||||
range_spec=RangeSpec(min=0.005, max=0.1, step=0.005),
|
||||
value=0.005,
|
||||
info="How much to weigh lexical scores compared to the embedding score. 0 means lexical search is not used at all, and 1 means only lexical search is used.",
|
||||
),
|
||||
MessageTextInput(
|
||||
name="filter",
|
||||
display_name="Metadata Filters",
|
||||
value="",
|
||||
info="The filter string to narrow the search to according to metadata attributes.",
|
||||
),
|
||||
DropdownInput(
|
||||
name="reranker",
|
||||
display_name="Reranker Type",
|
||||
options=RERANKER_TYPES,
|
||||
value=RERANKER_TYPES[0],
|
||||
info="How to rerank the retrieved search results.",
|
||||
),
|
||||
IntInput(
|
||||
name="reranker_k",
|
||||
display_name="Number of Results to Rerank",
|
||||
value=50,
|
||||
range_spec=RangeSpec(min=1, max=100, step=1),
|
||||
),
|
||||
FloatInput(
|
||||
name="diversity_bias",
|
||||
display_name="Diversity Bias",
|
||||
value=0.2,
|
||||
range_spec=RangeSpec(min=0, max=1, step=0.01),
|
||||
info="Ranges from 0 to 1, with higher values indicating greater diversity (only applies to MMR reranker).",
|
||||
),
|
||||
IntInput(
|
||||
name="max_results",
|
||||
display_name="Max Results to Summarize",
|
||||
value=7,
|
||||
range_spec=RangeSpec(min=1, max=100, step=1),
|
||||
),
|
||||
DropdownInput(
|
||||
name="response_lang",
|
||||
display_name="Response Language",
|
||||
options=["auto", "eng", "deu", "fra", "ita", "nld", "por", "rus", "spa", "zho"],
|
||||
value="eng",
|
||||
info="Use the ISO 639-1 or 639-3 language code or auto to automatically detect the language.",
|
||||
),
|
||||
DropdownInput(
|
||||
name="prompt",
|
||||
display_name="Prompt Name",
|
||||
options=SUMMARIZER_PROMPTS,
|
||||
value=SUMMARIZER_PROMPTS[0],
|
||||
info="Only vectara-summary-ext-24-05-sml is for Growth customers; all other prompts are for Scale customers only.",
|
||||
),
|
||||
]
|
||||
|
||||
outputs = [
|
||||
Output(name="answer", display_name="Answer", method="generate_response"),
|
||||
]
|
||||
|
||||
def generate_response(
|
||||
self,
|
||||
) -> Message:
|
||||
text_output = ""
|
||||
|
||||
try:
|
||||
from langchain_community.vectorstores import Vectara
|
||||
from langchain_community.vectorstores.vectara import RerankConfig, SummaryConfig, VectaraQueryConfig
|
||||
except ImportError:
|
||||
raise ImportError("Could not import Vectara. Please install it with `pip install langchain-community`.")
|
||||
|
||||
vectara = Vectara(self.vectara_customer_id, self.vectara_corpus_id, self.vectara_api_key)
|
||||
rerank_config = RerankConfig(self.reranker, self.reranker_k, self.diversity_bias)
|
||||
summary_config = SummaryConfig(
|
||||
is_enabled=True, max_results=self.max_results, response_lang=self.response_lang, prompt_name=self.prompt
|
||||
)
|
||||
config = VectaraQueryConfig(
|
||||
lambda_val=self.lexical_interpolation,
|
||||
filter=self.filter,
|
||||
summary_config=summary_config,
|
||||
rerank_config=rerank_config,
|
||||
)
|
||||
rag = vectara.as_rag(config)
|
||||
response = rag.invoke(self.search_query)
|
||||
|
||||
text_output = response["answer"]
|
||||
|
||||
return Message(text=text_output)
|
||||
|
|
@ -1013,7 +1013,7 @@ class Graph:
|
|||
next_runnable_vertices.remove(v_id)
|
||||
else:
|
||||
self.run_manager.add_to_vertices_being_run(next_v_id)
|
||||
if cache:
|
||||
if cache and self.flow_id:
|
||||
set_cache_coro = partial(get_chat_service().set_cache, key=self.flow_id)
|
||||
await set_cache_coro(self, lock)
|
||||
return next_runnable_vertices
|
||||
|
|
|
|||
|
|
@ -1,6 +1,7 @@
|
|||
from abc import ABC, abstractmethod
|
||||
from typing import TYPE_CHECKING, Any, Dict, Optional
|
||||
from uuid import UUID
|
||||
|
||||
from langflow.services.tracing.schema import Log
|
||||
|
||||
if TYPE_CHECKING:
|
||||
|
|
|
|||
11
src/backend/base/poetry.lock
generated
11
src/backend/base/poetry.lock
generated
|
|
@ -1850,17 +1850,6 @@ files = [
|
|||
{file = "mypy_extensions-1.0.0.tar.gz", hash = "sha256:75dbf8955dc00442a438fc4d0666508a9a97b6bd41aa2f0ffe9d2f2725af0782"},
|
||||
]
|
||||
|
||||
[[package]]
|
||||
name = "nanoid"
|
||||
version = "2.0.0"
|
||||
description = "A tiny, secure, URL-friendly, unique string ID generator for Python"
|
||||
optional = false
|
||||
python-versions = "*"
|
||||
files = [
|
||||
{file = "nanoid-2.0.0-py3-none-any.whl", hash = "sha256:90aefa650e328cffb0893bbd4c236cfd44c48bc1f2d0b525ecc53c3187b653bb"},
|
||||
{file = "nanoid-2.0.0.tar.gz", hash = "sha256:5a80cad5e9c6e9ae3a41fa2fb34ae189f7cb420b2a5d8f82bd9d23466e4efa68"},
|
||||
]
|
||||
|
||||
[[package]]
|
||||
name = "nest-asyncio"
|
||||
version = "1.6.0"
|
||||
|
|
|
|||
Loading…
Add table
Add a link
Reference in a new issue